PMC

https://pmc.ncbi.nlm.nih.gov/articles/PMC11637813/

Highlights

• Identifying a sufficient set of confounders is crucial for estimating the causal effect of exposure on outcome.
• We summarize approaches to identifying a sufficient set of confounders from both epidemiological and statistical perspectives.
• We also describe some pitfalls and considerations in confounder selection.
• E-value and robustness value are introduced as approaches to assess the sensitivity to unmeasured confounders.
• Integrating these principles and approaches will enhance our understanding of confounder selection in future epidemiological studies.

Selected Result